MétaCan
Menu
Back to cohort
Record W4318577134 · doi:10.1093/ecco-jcc/jjac190.0251

P121 Clinicomic profiles new feature patterns based on a simplified location classification for Crohn’s disease

2023· article· en· W4318577134 on OpenAlexaboutno aff
Wen Hu, Xiao Liang, Jia Luo, Peixing Li, Kimberly Shen, Jing Li, Shuyan Li, Jiazhan Xin, Jing Jiang, Dongyan Shi, Xuanding Wang, Danfeng Xu, Qi Yu, H Zhang, X Zhang, X Song, H Guo, Qingjie Ge, Yufeng Chen, Xi Chen, Yuchen Chen, J Li

Bibliographic record

VenueJournal of Crohn s and Colitis · 2023
Typearticle
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicInflammatory Bowel Disease
Canadian institutionsnot available
Fundersnot available
KeywordsCrohn's diseaseMedicineLinear discriminant analysisJejunumMedical diagnosisFeature (linguistics)Internal medicineGastroenterologyFeature selectionDiseaseArtificial intelligencePathologyComputer science

Abstract

fetched live from OpenAlex

Abstract Background Crohn’s disease (CD) is a heterogeneous and complicated condition that often has delayed diagnoses and poor outcomes. Disease location and site-specific mechanisms have received increasing attention in recent studies. Suboptimal classification adds complexity to clinical management for CD and the interpretation of its characteristics. This study aims to clarify the clinicopathological characteristics of CD patients through a prospective cohort. Methods The clinical data from 1173 patients with definite CD diagnoses and a simplified location classification based on anatomical traits (G1: esophagus+stomach+duodenum; G2: jejunum+ileum; G3: ileocecum; G4: colon+rectum) were used to clarify the feature patterns (Figure 1). Results Of the enrolled patients, 437 were newly diagnosed, and 736 were prevalent patients. A higher proportion of L4 involvement (45.8%) and a lower proportion of L2 (6.8%) patients were observed under the Montreal location classification. Single G2 (17.8%), G2+G3 (22.2%), G3+G4 (12.5%) and G2+G3+G4 (27.8%) were the four major types in the simplified location classification (Figure 2A-2B). The patients with G4 presented with higher C-reactive protein, G2 patients had more stricturing/penetrating behavior, and single G2 patients had the oldest age at diagnosis (Table 1). A clinicomic study with machine learning methods including principal component analysis, cluster analysis and partial least squares discriminant analysis, identified hemoglobin, platelet count and C-reactive protein as the three key indicators. A decision tree based on the three indicators and disease behavior stratified all patients into six feature patterns (simply/complicatedly active, simply/complicatedly anemia and simply/complicatedly stable), which formed a two-twisted-cycle model for natural disease history (Figure 2C). Most patients started their cycles at the active phase, and the “simply” cycle was mainly advanced by medications, while most patients in the “complicatedly” cycle needed multidisciplinary care. Comparisons among the six subgroups showed that age at diagnosis had the same rise-and-fall pattern as the G2+G4- proportion, while the G2-G4+ proportion showed the opposite trend (Table 2, Figure 2D-2E). An external validation group (n=301) confirmed the above results. The role of disease location could be interpreted as an important factor determining its start point and site-specific trajectory in the two-twisted-cycle model. Conclusion Site-specific clinical characteristics clarified by the simplified location classification, the new feature patterns profiled by the clinicomic study may provide new insights into CD phenotyping, risk stratification and precision treatment.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.004
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.003
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0000.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0040.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.021
GPT teacher head0.290
Teacher spread0.269 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Crohn s and ColitisSame topicInflammatory Bowel DiseaseFrench-language works237,207